Public beta

Built to make your local knowledge extraordinarily useful. Alfred is the AI-first workspace for everything you keep.

Alfred connects files, notes, concepts, and answers into a local graph you can inspect before AI takes action.

Download for macOS Install with Homebrew Download for Linux

Works withCodexClaude CodeOllamaOpenAIAnthropicOpenRouterConfluence

Search the graph and activate paths...270 nodes378 edges

Knowledge graph

Understands your entire workspace.

Alfred builds a knowledge graph across imported documents, notes, concepts, hubs, retrieval traces, and Dream maintenance so every answer can point back to evidence.

Document ingestion

Ingest every document without losing the original.

Drop Markdown, PDFs, images, JSON, YAML, CSV, or HTML. Alfred preserves the raw source, extracts structure, chunks evidence, and writes the graph only when the pipeline is traceable.

Open the ingestion pipeline

Inbox

Personal

Vision available

Local importVision available

Import documents

Drop Markdown, text, PDF, image, JSON, YAML, CSV, or HTML files here to send them through extraction, triage, content persistence, and knowledge sync.

Drag and drop files here

The active provider can inspect images and rendered PDF pages during import.

Queue

Import triage workbench for incoming documents.

2 items

logo-flame.png

Rendered 2/4 pages, running vision extraction.

624 KBProcessing

raw-sources.md

Content stored, extracting retrieval context...

18 KBDone

Confluence

Bring your Confluence space in without losing its structure.

Connect a Confluence space and Alfred imports pages with their hierarchy, triggers AI-generated descriptions through the provider you picked, and keeps the source link attached to every answer.

See Confluence import

ConfluenceSyncing 142 pages

Import space

Sync the Engineering space; generate descriptions for new pages.

Syncing 142 pages

ConfluenceComposer 2

Confluence / structured space

Space imported

Pages keep their hierarchy, ancestors, labels, and source URL. AI descriptions follow the provider you picked in Settings.

HierarchyAI descriptionsSource linkProvider-aware

Engineering / RFCs42 pages
ancestors retained3 levels
AI descriptionsvia provider

Multisearch

Search with vector, FTS, lexical, and time signals.

Ask one question and Alfred blends semantic recall, full-text search, lexical matching, and temporal context so the answer can cite the right source instead of the nearest embedding.

Explore multisearch

MCP long horizon

Use Alfred as a real MCP server for long work.

When you run Codex or Claude Code through Alfred, the CLI calls back into your workspace over a localhost MCP bridge — search memory, recall prior turns, inspect documents, resume with citations. Same loop with any external MCP client.

See MCP context

alfred-desktopMCP HTTP

mcpinitialize alfred-desktop @ http://127.0.0.1:51175/mcp

ok15 tools: recall, search, documents.list, documents.get_detail

youwhere did we leave the board update?

calltools/call recall({ query: "board update risks", sourceScopeName: "Memory" })

mem3 turns from mcp.save_interaction · repo alfred

calltools/call documents.list({ workspaceId: "personal", query: "board update" })

okBoard Update.md, Q2 Risks.pdf, Support Export.csv

calltools/call documents.get_detail({ documentId: "board-update" })

ansResume with churn risk, support signal, and two source citations.

Dream

Let the workspace improve while you are away.

Dream watches retrieval quality, concept drift, stale sources, and graph candidates, then keeps routine maintenance automatic while logging risky or ambiguous changes.

Open Dream autopilot

Bring your own AI

Use the subscription you already pay for.

Run Codex or Claude Code through your terminal — or run Ollama locally, or bring an OpenAI, Anthropic, or OpenRouter key. Alfred routes every Ask, ingestion, and tool call through the provider you pick.

Subscription CLIs

Claude Code^Pro

Codex^Plus

Local LLM

Ollama127.0.0.1:11434

4 models

API keys

OpenAI

Anthropic

OpenRouter

macOS + Linux beta

Build your local graph.

Download the latest signed macOS DMG, Ubuntu/Debian package, or universal Linux AppImage from GitHub Releases. macOS users can also install through the Homebrew cask.

macOS Homebrewbrew install --cask alfred-labs/alfred/alfred-app

Ubuntu / Debian (.deb)

Download the latest .deb package directly and open it with your package installer.

Other Linux (universal AppImage)

chmod +x Alfred-latest-linux-x86_64.AppImage
./Alfred-latest-linux-x86_64.AppImage

Release notes